Information processing methods, computer programs, and information processing devices.

Abstract

This enables improved accuracy in customer analysis. [Solution] Associating relevant attribute information that indicates the characteristics of the store with the store, An information processing method that includes assigning relevant attribute information of the store to which a payment was made to the user, based on the user's payment to the store.

Description

Technical Field

[0001] The present invention relates to an information processing method, a computer program, and an information processing apparatus.

Background Art

[0002] Conventionally, customers have been classified based on their registration information and performance information. For example, in the technology disclosed in Patent Document 1, customers are classified into groups according to the characteristics and attributes of each customer. For example, regarding credit card customers, classification is performed based on information such as age, place of residence, and the amount of card usage.

Prior Art Documents

Patent Documents

[0003]

Patent Document 1

Summary of the Invention

Problems to be Solved by the Invention

[0004] However, sufficient accuracy has not always been ensured for customer classification. Such problems were common not only in classification but also when performing any analysis on customers.

[0005] The present invention has been made in view of the above circumstances, and provides a technology that enables improvement in the accuracy of customer analysis.

Means for Solving the Problems

[0006] One aspect of the present invention is an information processing method including associating related attribute information indicating characteristics of a store with the store, and assigning the related attribute information of the store where a user has made a payment to the user based on the fact that the user has made a payment to the store.

[0007] One aspect of the present invention is the above-described information processing method, wherein the user is assigned relevant attribute information of the store where the payment was made, using a priority based on the number of times the user has made payments at the store.

[0008] One aspect of the present invention is the above-described information processing method, wherein the user is assigned relevant attribute information of the store where the payment was made, using a priority based on the amount of payment the user made at the store.

[0009] One aspect of the present invention is the above-described information processing method, which classifies users who are likely to have a high level of interest in a particular field based on user information to which the relevant attribute information has been assigned.

[0010] One aspect of the present invention is the above-described information processing method, wherein information showing the correlation of each related attribute information with respect to each group is output based on the related attribute information and the group to which the user possessing the related attribute information belongs.

[0011] One aspect of the present invention is the above-described information processing method, wherein, based on the related attribute information, information is output indicating whether or not the user accepts a predetermined measure.

[0012] One aspect of the present invention is the above-described information processing method, wherein, with respect to the user to be analyzed, information indicating changes in the user to be analyzed between two timings is output based on relevant attribute information at a first timing and relevant attribute information at a second timing different from the first timing.

[0013] One aspect of the present invention is a computer program for causing a computer to function as an information processing device that includes a control unit that associates relevant attribute information indicating the characteristics of a store with a store, and provides the user with relevant attribute information of the store to which payment was made based on the user's payment to the store.

[0014] One aspect of the present invention is an information processing apparatus including a control unit that associates relevant attribute information indicating characteristics of a store with the store and assigns the relevant attribute information of the store where a user has made a payment to the user based on the fact that the user has made a payment to the store.

Advantages of the Invention

[0015] According to the present invention, it becomes possible to improve the accuracy in customer analysis.

Brief Description of the Drawings

[0016] [Figure 1] It is a schematic block diagram showing the system configuration of the information processing system 100 of the present invention. [Figure 2] It is a schematic block diagram showing a specific example of the functional configuration of the analysis device 30. [Figure 3] It is a diagram showing a specific example of the store information table stored in the store information storage unit 321. [Figure 4] It is a diagram showing a specific example of the transaction information table stored in the transaction information storage unit 322. [Figure 5] It is a diagram showing a specific example of the user information table stored in the user information storage unit 323. [Figure 6] It is a diagram showing a specific example of the relevant attribute information table stored in the relevant attribute information storage unit 324. [Figure 7] It is a diagram showing an outline of a hardware configuration example of the information processing apparatus 90 applied to the present embodiment. [Figure 8] It is a diagram showing a specific example of the brand information table stored in the brand information storage unit. [Figure 9] It is a diagram showing a modified example of the store information table stored in the store information storage unit 321.

Embodiments for Carrying Out the Invention

[0017] FIG. 1 is a schematic block diagram showing the system configuration of the information processing system 100 of the present invention. The information processing system 100 includes a store terminal device 11, a user terminal device 12, a merchant server 13, a settlement control device 20, and an analysis device 30. The store terminal device 11, the user terminal device 12, the merchant server 13, the settlement control device 20, and the analysis device 30 are communicably connected to each other via a network 70. The network 70 may be a network using wireless communication or a network using wired communication. The network 70 may be configured using, for example, the Internet or a local area network (LAN). The network 70 may be configured by combining a plurality of networks.

[0018] The store terminal device 11 is a device used when a customer makes a payment without using cash at a store. The store terminal device 11 is an information processing device such as a smartphone, a tablet device, or a dedicated device. The store terminal device 11 may be operated by a person related to the store where the device (store terminal device 11) is installed (such as an owner or an employee), or may be operated by the customer himself / herself who intends to make a payment. When the store terminal device 11 is operated by a person related to the store, so-called face-to-face settlement is performed. Also, when the store terminal device 11 is operated by the customer himself / herself, so-called self-checkout settlement is performed.

[0019] The settlement using the store terminal device 11 may be, for example, a settlement using a credit card, a settlement using electronic money, a settlement using a barcode, a settlement using points, or a settlement by other means. The store terminal device 11 performs settlement for the customer's payment to the store by communicating with the settlement control device 20 according to a predetermined settlement protocol.

[0020] The user terminal device 12 is a device used when a customer makes a cashless payment without communicating with the store terminal device 11. The user terminal device 12 is an information processing device owned by the user themselves. The user terminal device 12 is, for example, an information processing device such as a smartphone, tablet device, or personal computer. The user terminal device 12 purchases desired goods or services by communicating with the business server 13, for example, depending on the operation of an application or web browser that is pre-installed on the device. Regarding payment at the time of purchase, the user terminal device 12 makes the payment by communicating with the payment control device 20 using a predetermined payment protocol. Payment using such a user terminal device 12 is carried out as so-called non-face-to-face payment (online payment).

[0021] The business operator server 13 is a device that sells or provides goods or services via a network by communicating with the user terminal device 12. The business operator server 13 is configured using, for example, an information processing device such as a personal computer or server equipment. The business operator server 13 may be a device installed to assist in the operation of multiple online shops, such as a network mall, or it may be a device installed by a store. The owner of the business operator server 13 may enable payment to be made via communication between the business operator server 13 and the payment control device 20 by, for example, entering into a contract with a specific payment service provider in advance.

[0022] The payment control device 20 is an information processing device operated by a payment service provider. Examples of payment service providers include credit card companies, electronic money companies, barcode payment companies, and point service providers. The payment control device 20 performs payments made by customers to stores by communicating with devices such as store terminals 11, user terminals 12, and service provider servers 13 using a predetermined payment protocol. The payment control device 20 transmits information regarding the payment history to the analysis device 30.

[0023] Figure 2 is a schematic block diagram showing a specific example of the functional configuration of the analysis device 30. The analysis device 30 is configured using information processing equipment such as a personal computer or a server device. The analysis device 30 includes a communication unit 31, a storage unit 32, and a control unit 33.

[0024] The communication unit 31 is a communication device. The communication unit 31 may be configured, for example, as a network interface. The communication unit 31 communicates data with other devices via the network 70 in accordance with the control of the control unit 33. The communication unit 31 may be a device that performs wireless communication or a device that performs wired communication.

[0025] The storage unit 32 is configured using a storage device such as a magnetic hard disk drive or a semiconductor storage device. The storage unit 32 stores data used by the control unit 33. The storage unit 32 may function as, for example, a store information storage unit 321, a transaction information storage unit 322, a user information storage unit 323, and a related attribute information storage unit 324.

[0026] The store information storage unit 321 stores store information. Store information indicates information about an entity that sells goods or provides services. In this embodiment, such an entity is referred to as a store. A store may refer to a physically existing store or a virtual store that exists on a network.

[0027] Figure 3 shows a specific example of a store information table stored by the store information storage unit 321. The store information table has multiple store information records. Each store information record has values ​​for store identification information, name, location information, address, industry, and related attribute information. Store identification information is identification information that uniquely identifies each store. Name indicates the name of each store. Location information indicates the location information (e.g., latitude and longitude) of each store. Address indicates the address of each store. Industry indicates the industry of each store. Related attribute information indicates related attribute information assigned to each store. Related attribute information is text that indicates the characteristics and attributes related to each store. For example, as shown in Figure 3, the related attribute information for the store identified by store identification number SH01 is stationery, studying, and high-end fountain pens. Related attribute information may be determined as text that indicates the characteristics of each store based on images and text used on websites and social media operated by each store. Alternatively, it may be determined as text that indicates the characteristics of each store based on images and text related to each store on websites and social media operated by parties other than each store. Such determinations may be made, for example, by a human, or by software such as a generative AI. The number of related attribute information items defined for a single store may be determined as a constant, or the maximum and minimum values ​​of that number may be determined.

[0028] Figure 4 shows a specific example of a transaction information table stored in the transaction information storage unit 322. The transaction information table has multiple transaction information records. Each transaction information record shows information about individual settlement transactions performed by the settlement control device 20. Each transaction information record has user identification information, store identification information, date, and transaction information values. User identification information is identification information that uniquely identifies each user (customer). In the transaction information, the user is the entity that made the payment related to the settlement as a customer. Store identification information indicates the identification information of the store where the payment related to the settlement was made. The date indicates the date on which the payment related to the settlement was made. Transaction information shows information related to the settlement. In the specific example in Figure 4, the transaction information shows the amount paid in the settlement. Transaction information may also be information transmitted from the settlement control device 20 to the analysis device 30, for example.

[0029] Figure 5 shows a specific example of a user information table stored in the user information storage unit 323. The user information table has multiple user information records. Each user information record has values ​​for user identification information, gender, address, and transaction history information. User identification information is identification information that uniquely identifies each user. Gender indicates the gender of each user. Address indicates the address of each user. Transaction history information shows statistical information of settlement transactions related to payments made by each user. In the example in Figure 5, the transaction history information shows store identification information, the number of times payments have been made, and a statistical value of the payment amount (e.g., average) for each store where a payment has been made. The statistical value of the payment amount may be the average value, or it may be other statistical values ​​(maximum value, mode, sum, etc.).

[0030] Figure 6 shows a specific example of a related attribute information table stored by the related attribute information storage unit 324. The related attribute information table has multiple related attribute information records. Each related attribute information record has user identification information and related attribute information values. User identification information is identification information that uniquely identifies each user. Related attribute information is related attribute information assigned to each user. The related attribute information assigned to each user is assigned according to the related attribute information of the stores where each user has made payments (hereinafter referred to as "actual stores"). For example, each user may be assigned related attribute information defined for that user's actual stores. For example, each user may be assigned related attribute information based on a priority determined based on the number of payments and payment amount at that user's actual stores. In Figure 6, the related attribute information is also assigned a value indicating priority. In Figure 6, the numbers shown in parentheses indicate the priority. Priority indicates the degree of priority given to which related attribute information is assigned first when assigning related attribute information to each user; the higher the priority, the more preferentially it is assigned to the user.

[0031] The control unit 33 is composed of a processor such as a CPU (Central Processing Unit) and memory (main memory). The control unit 33 functions as an information control unit 331, a related attribute information determination unit 332, an analysis unit 333, and a post-processing unit 334 when the processor executes a program. Note that all or part of the functions of the control unit 33 may be implemented using hardware such as an ASIC (Application Specific Integrated Circuit), a PLD (Programmable Logic Device), or an FPGA (Field Programmable Gate Array). The above program may be recorded on a computer-readable recording medium. Computer-readable recording media include, for example, portable media such as flexible disks, magneto-optical disks, ROMs, CD-ROMs, and semiconductor memory devices (e.g., SSDs: Solid State Drives), as well as storage devices such as hard disks and semiconductor memory devices built into computer systems. The above program may also be transmitted via a telecommunications line.

[0032] The information control unit 331 controls the input and output of information. For example, the information control unit 331 acquires data from other devices (information processing devices and storage media) and records it in the storage unit 32. For example, the information control unit 331 transmits data generated by the analysis unit 333 to other devices.

[0033] The related attribute information determination unit 332 assigns related attribute information to users. The related attribute information determination unit 332 assigns related attribute information according to the related attribute information of stores where each user has made payments (actual stores). For example, the related attribute information determination unit 332 assigns each user the related attribute information defined for the user's actual stores. More specifically, the related attribute information determination unit 332 determines a priority for each user based on the number of payments and payment amount at the user's actual stores, and assigns related attribute information based on the priority. For example, the related attribute information determination unit 332 may assign a predetermined number of related attribute pieces to each user in order of priority.

[0034] The related attribute information determination unit 332 assigns a higher priority to related attribute information defined in stores where the user has made more payments, for example. The related attribute information determination unit 332 assigns a higher priority to related attribute information defined in stores where the user has paid a higher statistical value for that user, for example. The transaction history information for each user stored in the user information storage unit 323 may be generated by the related attribute information determination unit 332 or by another device (for example, the payment control device 20).

[0035] The analysis unit 333 performs analysis based on the contents of the related attribute information table stored in the related attribute information storage unit 324. The post-processing unit 334 performs predetermined processing according to the analysis results of the analysis unit 333. Specific examples of the processing performed by the analysis unit 333 and the post-processing unit 334 are described below.

[0036] The first aspect of the processing performed by the analysis unit 333 and the post-processing unit 334 is user classification and processing according to the classification results. The analysis unit 333 may classify users based on related attribute information associated with each user stored in the related attribute information storage unit 324, for example. For example, processing may be performed to classify users who are likely to have a high interest in a particular field. In this case, the classification may be performed by determining one or more related attribute pieces of information related to the field to be processed and extracting users to whom that related attribute information is assigned. For example, related attribute information such as sports, exercise, diet, yoga, and health may be determined as related attribute information related to the field of health promotion, and users to whom each piece of related attribute information is assigned may be classified as users who are likely to have a high interest in the field of health promotion. The determination of one or more related attribute pieces of information related to the field to be processed may be performed by a person, based on a predefined table, or using generative AI technology using LLM (Large Language Models).

[0037] When extracting users with relevant attribute information, all users with relevant attribute information may be extracted regardless of priority, or only users with a priority value of a certain level or higher may be extracted. The former method allows for the extraction of a wider range of users, while the latter method allows for the precise extraction of only users who are more likely to be interested.

[0038] The post-processing unit 334 performs predetermined post-processing according to the results of the analysis unit 333. For example, the post-processing unit 334 may provide the analysis results of the analysis unit 333 to the client who requested the analysis. In this case, the fields of the processing targets that form the basis of classification in the analysis unit 333 may be information provided by the client. Such information may be transmitted from the client's information processing device via a network and acquired by the information control unit 331, or it may be input into the analysis device 30 by the user of the analysis device 30.

[0039] The post-processing unit 334 may create a report to be provided to the client based on the analysis results in a predetermined format, and may transmit the electronic data of the created report to the client's information processing device. The post-processing unit 334 may also print the report using an image forming device such as a multifunction printer. In this case, the printed report may be mailed to the client by a person.

[0040] The post-processing unit 334 may send predetermined information, such as emails, to individuals classified by the analysis unit 333. For example, it may perform processing to send information such as direct messages, email newsletters, or SMS related to the field being processed to each classified user. If printed materials are sent to each user as direct messages, the post-processing unit 334 may read the addresses of each classified user from the user information storage unit 323 and send the read address information to another device (for example, a device that manages the sending of direct messages). If electronic data is sent to each user as an email newsletter or SMS, the post-processing unit 334 may read the destinations (email addresses or mobile phone numbers) of each classified user from the user information storage unit 323 and send predetermined data to the read destinations. In this case, it is desirable that the user information storage unit 323 has data for each user's destinations registered.

[0041] A second aspect of the processing by the analysis unit 333 and the post-processing unit 334 is the analysis of users' hobbies and preferences in a predetermined region. The analysis unit 333 may, for example, extract users related to the predetermined region being processed and analyze user trends in the predetermined region based on the relevant attribute information assigned to those users. Extraction of users related to the predetermined region may, for example, involve extracting users who have a payment history at stores located in the predetermined region, or users who have an address in the predetermined region, or both. The analysis unit 333 may read the relevant attribute information assigned to the extracted users and analyze areas that are likely to be of high interest in that region. Such analysis processing allows for more effective market area analysis. For example, by comparing the relevant attribute information of a market area to be analyzed with a market area to be compared, it is possible to grasp the characteristics of the market area and support store opening plans, etc. The processing of the post-processing unit 334 is the same as in the first aspect.

[0042] The post-processing unit 334 or a person may use external media to approach each user and develop services. Furthermore, differences between user groups may be determined based on differences in the assignment of relevant attribute information among certain user groups. Such determination results can be used in product design, strategy development, etc. It is also possible to provide analysis and statistical data at a level requested by the client. In addition, after these processes by the post-processing unit 334, the analysis unit 333 may calculate the response rate to those processes. Such a response rate may be calculated, for example, by comparing payment history (e.g., statistical values ​​of the number of payments and payment amounts) before and after post-processing for a user group formed by multiple users who were the target of the post-processing.

[0043] Figure 7 is a schematic diagram of an example hardware configuration of an information processing device 90 applied to this embodiment. The information processing device 90 comprises a processor 91, main memory 92, communication interface 93, auxiliary storage device 94, input / output interface 95, and internal bus 96. The processor 91, main memory 92, communication interface 93, auxiliary storage device 94, and input / output interface 95 are connected to each other via the internal bus 96 so as to be able to communicate with each other. The information processing device 90 may be applied to, for example, an analysis device 30. In this case, for example, the communication unit 31 may be configured using the communication interface 93. For example, the storage unit 32 may be configured using the auxiliary storage device 94. Also, the control unit 33 may be configured using the processor 91 and the main memory 92.

[0044] In this embodiment, configured as described above, it becomes possible to improve the accuracy of customer analysis. Specifically, this is as follows: For example, it was difficult to achieve sufficient accuracy when trying to classify customers based on the type of business at the store where they used their cards. For example, even within the food retail industry, stores that mainly sell high-end ingredients and stores that mainly sell discounted items to the general public may actually be used by different types of customers. Therefore, even if information about the latter type of retail store is provided to customers who mainly use the former type of retail store, it may not be useful information. In other words, it may not have been possible to accurately classify customers. To address this problem, this system does not classify customers simply based on the type of business at the store where they used their cards, but rather performs the following processing. First, one or more relevant attribute pieces of information that indicate the characteristics of each store are assigned in advance. Then, the relevant attribute pieces of the store are assigned to customers (users) who have used that store. When it is necessary to classify customers, analysis such as classification is performed based on the relevant attribute pieces of information assigned to each customer. Therefore, it is possible to achieve a higher accuracy of analysis compared to when analysis such as classification is performed simply based on the type of business at the store used.

[0045] Furthermore, users who are determined to have a high level of interest in a particular field through such analysis may be sent information related to that field (e.g., advertisements or direct messages). This process makes it possible to appropriately approach users who have a potential interest in a particular field but who have not been reached before.

[0046] (modified version) The analysis device 30 may further include a brand information storage unit. A brand may represent a business operator that operates multiple stores, or it may represent multiple different brands operated by the same business operator. Figure 8 shows a specific example of a brand information table stored in the brand information storage unit. The brand information table has multiple brand information records. Each brand information record has values ​​for brand identification information, brand name, industry, and related attribute information.

[0047] Brand identification information is unique identification information that identifies each brand. Brand name indicates the name of each brand. Industry indicates the industry of each brand. Related attribute information indicates related attribute information assigned to each brand. In this case, related attribute information is wording that indicates the characteristics or attributes associated with each brand. Related attribute information assigned to a brand may be determined as wording that indicates the characteristics of each brand based on images and wording used on websites and social media operated by each brand, or it may be determined as wording that indicates the characteristics of each brand based on images and wording related to each brand used on websites and social media operated by parties other than each brand. Such determination may be performed by a human, or by software such as a generative AI. The number of related attribute information items defined for a single brand may be determined to be a constant, or the maximum and minimum values ​​of that number may be determined.

[0048] Figure 9 shows a modified example of the store information table stored by the store information storage unit 321. In the modified example shown in Figure 9, the store information table further includes brand identification information values. The brand identification information values ​​indicate the brand to which the store in that store information table belongs. In the modified example, the related attribute information in the store information table may include not only related attribute information directly assigned to the store, but also related attribute information assigned to the brand to which the store belongs.

[0049] For example, both the SH02 store and the SH04 store belong to the same BR2 brand. Therefore, both the SH02 store and the SH04 store are assigned the same attribute information for "coffee" and "baked goods" that is associated with the BR2 brand. Furthermore, the SH02 store is assigned unique attribute information unrelated to the brand, such as "open late at night" and "located in front of a train station." Similarly, the SH04 store is assigned unique attribute information unrelated to the brand, such as "located in the suburbs" and "closes early."

[0050] The user information table shown in Figure 5 may be configured so as not to contain transaction history information. In this configuration, the control unit 33 (for example, the related attribute information determination unit 332) may assign related attribute information to the user based on the transaction information and user information stored in the transaction information storage unit 322 shown in Figure 4.

[0051] (Examples of application) A specific example of the processing when the analytical device 30 of this embodiment is applied to a more specific analysis will be described. In the following description, customer analysis in credit card payments will be used as a specific example, but customer analysis in other cashless payment methods may also be used.

[0052] 1. First application example Define any group of comparison targets for identifying the persona of a cardholder. For example, define a first group and a second group. For instance, the first group could be defined as members who hold family cards, and the second group as members who do not hold family cards. The number of groups defined for comparison is not limited to two. For example, three or more groups may be defined. For instance, the first group could be defined as general members, the second group as gold members, and the third group as platinum members. Consider the differences in the relevant attribute information assigned to members between the defined groups, and obtain the relevant attribute information that has the greatest impact on each group. The results of such analysis may be used to interpret the persona of members belonging to each group based on the relevant attribute information that appeared most frequently in each group.

[0053] In this case, the following processing may be performed: For each group, relevant attribute information for card members belonging to that group is used as an explanatory variable, and the value representing the group becomes the target variable. In this case, the value of the group to which each user belongs must be defined as user information. For example, a trained model may be generated by performing a training process using the actual information stored in the memory unit 32 as training data for the above-mentioned combination of explanatory and target variables. There are methods for extracting important explanatory variables (relevant attribute information) from Permutation Importance and SHAP Importance. For example, correlation values ​​for each piece of relevant attribute information with respect to the target variable may be obtained. Based on such analysis results, product design may be carried out for members belonging to each group based on the relevant attribute information that has a high impact in each group.

[0054] 2.Second application example In the second application example, relevant attribute information is used to determine whether or not a member has accepted a predetermined measure (e.g., a credit card upgrade measure). For example, relevant attribute information of members holding a predetermined grade of card (e.g., a standard card with no annual fee) may be used as explanatory variables, and whether or not those members have been upgraded in past upgrade measures may be used as the dependent variable. A trained model may be generated by performing a training process using past performance data as training data. Members who have obtained a high score for the dependent variable of upgrading, obtained by performing an inference process using such a trained model, may be selected as the target recipients for the upgrade measure. Such a trained model may be generated using, for example, performance data obtained for members of each grade as training data. By configuring it in this way, it is possible to improve the accuracy of inference.

[0055] 3.Third application example In the third application example, relevant attribute information is used in cross-selling strategies. For example, if a specific strategy has been implemented in the past, the members to whom that strategy was implemented can be identified, and the presence or absence of purchasing behavior (usage behavior) of those members can be determined. For example, a trained model can be generated by using the relevant attribute information of the members targeted by the cross-selling strategy as explanatory variables, information indicating the past purchasing behavior of members with that relevant attribute information as the dependent variable, and using past performance data as training data. By providing the relevant attribute information of the target of analysis as an explanatory variable to such a trained model and performing inference processing, it becomes possible to infer information indicating the purchasing behavior when a cross-selling strategy is implemented for members with that relevant attribute information. If no strategy has been implemented in the past, a pseudo-group of target members can be created, and the presence or absence of purchasing behavior can be determined.

[0056] 4.Fourth application example In the fourth application example, an analysis of changes in a user is performed based on relevant attribute information recorded at a first time point and relevant attribute information recorded at a second time point (a time point different from the first time point) for a predetermined target user. A concrete example of a change in a user is a change in the user's hobbies and preferences. For example, if a target user was assigned the relevant attribute information of "fast food" at the first time point (e.g., 2022), but was assigned the relevant attribute information of "natural foods" at the second time point (e.g., 2025), the following change analysis results can be obtained. Based on the analysis results, actions (e.g., advertising methods) directed at the target user can be determined. • First analysis result: It is presumed that the user has started to become health-conscious. It has been decided to send direct mail (DM) about health-related products (supplements, etc.) to this user. Second analysis result: It is presumed that the user got married and their family has grown. It has been decided to implement PR measures (such as sending direct mail) for products aimed at newlyweds for this user.

[0057] In this embodiment, the payment control device 20 and the analysis device 30 are configured as separate devices, but they may be configured as a single integrated device.

[0058] The analysis device 30 may be implemented using multiple information processing devices. For example, the analysis device 30 may be implemented using a device such as a cloud. For example, in the analysis device 30, the storage unit 32 and the control unit 33 may be implemented on different information processing devices. For example, the storage unit 32 of the analysis device 30 may be distributed and implemented on multiple information processing devices, or the control unit 33 of the analysis device 30 may be distributed and implemented on multiple information processing devices.

[0059] While embodiments of this invention have been described in detail above with reference to the drawings, the specific configuration is not limited to these embodiments and includes designs and the like that do not depart from the spirit of this invention. [Explanation of Symbols]

[0060] 100…Information processing system, 11…Store terminal device, 12…User terminal device, 13…Business operator server, 20…Payment control device 20, 30…Analysis device, 31…Communication unit, 32…Storage unit, 321…Store information storage unit, 322…Transaction information storage unit, 323…User information storage unit, 324…Related attribute information storage unit, 33…Control unit, 331…Information control unit, 332…Related attribute information determination unit, 333…Analysis unit, 334…Post-processing unit

Claims

1. Associating relevant attribute information that indicates the characteristics of the store with the store, This includes providing the user with relevant attribute information of the store to which the payment was made, based on the user's payment to the store. When assigning the user the relevant attribute information of the store where payment was made, the relevant attribute information of the store where payment was made is assigned to the user using a priority system based on the number of times the user has made payments at that store. Furthermore, this information processing method generates a trained model by performing a learning process using past performance data as training data, with the relevant attribute information of users who possess a predetermined grade of credit card as an explanatory variable, and whether or not those users have upgraded in past upgrade measures as the dependent variable.

2. The information processing method according to claim 1, further comprising extracting users who have obtained a high score for the objective variable "upgrade" by performing an inference process using the trained model.

3. The information processing method according to claim 1, wherein the user is assigned relevant attribute information of the store where he made a payment, using priority based on the amount of payment the user made at the store.

4. The information processing method according to claim 1, which classifies users who are likely to have a high level of interest in a particular field based on user information to which the aforementioned related attribute information has been assigned.

5. The information processing method according to claim 1, which outputs information showing the correlation of each related attribute piece for each group, based on the related attribute information and the group to which the user possessing the related attribute information belongs.

6. The information processing method according to claim 1, which outputs information indicating whether the user accepts a predetermined measure based on the aforementioned related attribute information.

7. The information processing method according to claim 1, which outputs information indicating changes in the user being analyzed between two timings, based on relevant attribute information at a first timing and relevant attribute information at a second timing different from the first timing, for the user being analyzed.

8. The system includes a control unit that associates relevant attribute information indicating the characteristics of a store with the store, and, based on the user making a payment to the store, provides the user with relevant attribute information of the store to which the payment was made. When the control unit provides the user with attribute information of the store where payment was made, it uses a priority system based on the number of times the user has made payments at the store to provide the user with attribute information of the store where payment was made. The control unit is further a computer program for causing a computer to function as an information processing device that generates a trained model by performing a learning process using past performance data as training data, with the relevant attribute information of users who possess a predetermined grade of credit card as explanatory variables, and whether or not those users have upgraded in past upgrade measures as the objective variable.

9. The system includes a control unit that associates relevant attribute information indicating the characteristics of a store with the store, and, based on the user making a payment to the store, provides the user with relevant attribute information of the store to which the payment was made. When the control unit provides the user with attribute information of the store where payment was made, it uses a priority system based on the number of times the user has made payments at the store to provide the user with attribute information of the store where payment was made. The control unit further generates a trained model by performing a learning process using past performance data as training data, with the relevant attribute information of users who possess a predetermined grade of credit card as explanatory variables, and whether or not those users have upgraded in past upgrade measures as the objective variable.

Images